gvaya-bsc commited on
Commit
137c446
·
verified ·
1 Parent(s): 035f23b

Initial model upload

Browse files
Files changed (3) hide show
  1. README.md +199 -0
  2. config.json +232 -0
  3. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/gpfs/projects/bsc14/gvaya/GLiClass/model_final",
3
+ "architecture_type": "uni-encoder",
4
+ "architectures": [
5
+ "DebertaForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "class_token_index": 128001,
9
+ "contrastive_loss_coef": 0.0,
10
+ "embed_class_token": true,
11
+ "encoder_config": {
12
+ "_attn_implementation_autoset": false,
13
+ "_name_or_path": "./deberta",
14
+ "add_cross_attention": false,
15
+ "architectures": [
16
+ "DebertaV2Model"
17
+ ],
18
+ "attention_probs_dropout_prob": 0.1,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": null,
22
+ "chunk_size_feed_forward": 0,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": null,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "hidden_act": "gelu",
35
+ "hidden_dropout_prob": 0.1,
36
+ "hidden_size": 768,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "is_decoder": false,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "layer_norm_eps": 1e-07,
50
+ "legacy": true,
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 512,
54
+ "max_relative_positions": -1,
55
+ "min_length": 0,
56
+ "model_type": "deberta-v2",
57
+ "no_repeat_ngram_size": 0,
58
+ "norm_rel_ebd": "layer_norm",
59
+ "num_attention_heads": 12,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_hidden_layers": 6,
63
+ "num_return_sequences": 1,
64
+ "output_attentions": false,
65
+ "output_hidden_states": false,
66
+ "output_scores": false,
67
+ "pad_token_id": 0,
68
+ "pooler_dropout": 0,
69
+ "pooler_hidden_act": "gelu",
70
+ "pooler_hidden_size": 768,
71
+ "pos_att_type": [
72
+ "p2c",
73
+ "c2p"
74
+ ],
75
+ "position_biased_input": false,
76
+ "position_buckets": 256,
77
+ "prefix": null,
78
+ "problem_type": null,
79
+ "pruned_heads": {},
80
+ "relative_attention": true,
81
+ "remove_invalid_values": false,
82
+ "repetition_penalty": 1.0,
83
+ "return_dict": true,
84
+ "return_dict_in_generate": false,
85
+ "sep_token_id": null,
86
+ "share_att_key": true,
87
+ "suppress_tokens": null,
88
+ "task_specific_params": null,
89
+ "temperature": 1.0,
90
+ "tf_legacy_loss": false,
91
+ "tie_encoder_decoder": false,
92
+ "tie_word_embeddings": true,
93
+ "tokenizer_class": null,
94
+ "top_k": 50,
95
+ "top_p": 1.0,
96
+ "torch_dtype": "float32",
97
+ "torchscript": false,
98
+ "type_vocab_size": 0,
99
+ "typical_p": 1.0,
100
+ "use_bfloat16": false,
101
+ "vocab_size": 128003
102
+ },
103
+ "encoder_model_name": "./deberta",
104
+ "extract_text_features": false,
105
+ "focal_loss_alpha": -1,
106
+ "focal_loss_gamma": -1,
107
+ "hidden_act": "gelu",
108
+ "hidden_dropout_prob": 0.1,
109
+ "hidden_size": 768,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1",
113
+ "2": "LABEL_2"
114
+ },
115
+ "ignore_index": -100,
116
+ "initializer_range": 0.03,
117
+ "intermediate_size": 3072,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1,
121
+ "LABEL_2": 2
122
+ },
123
+ "label_model_config": {
124
+ "_attn_implementation_autoset": false,
125
+ "_name_or_path": "BAAI/bge-small-en-v1.5",
126
+ "add_cross_attention": false,
127
+ "architectures": [
128
+ "BertModel"
129
+ ],
130
+ "attention_probs_dropout_prob": 0.1,
131
+ "bad_words_ids": null,
132
+ "begin_suppress_tokens": null,
133
+ "bos_token_id": null,
134
+ "chunk_size_feed_forward": 0,
135
+ "classifier_dropout": null,
136
+ "cross_attention_hidden_size": null,
137
+ "decoder_start_token_id": null,
138
+ "diversity_penalty": 0.0,
139
+ "do_sample": false,
140
+ "early_stopping": false,
141
+ "encoder_no_repeat_ngram_size": 0,
142
+ "eos_token_id": null,
143
+ "exponential_decay_length_penalty": null,
144
+ "finetuning_task": null,
145
+ "forced_bos_token_id": null,
146
+ "forced_eos_token_id": null,
147
+ "hidden_act": "gelu",
148
+ "hidden_dropout_prob": 0.1,
149
+ "hidden_size": 384,
150
+ "id2label": {
151
+ "0": "LABEL_0"
152
+ },
153
+ "initializer_range": 0.02,
154
+ "intermediate_size": 1536,
155
+ "is_decoder": false,
156
+ "is_encoder_decoder": false,
157
+ "label2id": {
158
+ "LABEL_0": 0
159
+ },
160
+ "layer_norm_eps": 1e-12,
161
+ "length_penalty": 1.0,
162
+ "max_length": 20,
163
+ "max_position_embeddings": 512,
164
+ "min_length": 0,
165
+ "model_type": "bert",
166
+ "no_repeat_ngram_size": 0,
167
+ "num_attention_heads": 12,
168
+ "num_beam_groups": 1,
169
+ "num_beams": 1,
170
+ "num_hidden_layers": 12,
171
+ "num_return_sequences": 1,
172
+ "output_attentions": false,
173
+ "output_hidden_states": false,
174
+ "output_scores": false,
175
+ "pad_token_id": 0,
176
+ "position_embedding_type": "absolute",
177
+ "prefix": null,
178
+ "problem_type": null,
179
+ "pruned_heads": {},
180
+ "remove_invalid_values": false,
181
+ "repetition_penalty": 1.0,
182
+ "return_dict": true,
183
+ "return_dict_in_generate": false,
184
+ "sep_token_id": null,
185
+ "suppress_tokens": null,
186
+ "task_specific_params": null,
187
+ "temperature": 1.0,
188
+ "tf_legacy_loss": false,
189
+ "tie_encoder_decoder": false,
190
+ "tie_word_embeddings": true,
191
+ "tokenizer_class": null,
192
+ "top_k": 50,
193
+ "top_p": 1.0,
194
+ "torch_dtype": "float32",
195
+ "torchscript": false,
196
+ "type_vocab_size": 2,
197
+ "typical_p": 1.0,
198
+ "use_bfloat16": false,
199
+ "use_cache": true,
200
+ "vocab_size": 30522
201
+ },
202
+ "label_model_name": "BAAI/bge-small-en-v1.5",
203
+ "layer_norm_eps": 1e-07,
204
+ "legacy": true,
205
+ "logit_scale_init_value": 2.6592,
206
+ "max_num_classes": 25,
207
+ "max_position_embeddings": 512,
208
+ "max_relative_positions": -1,
209
+ "model_type": "deberta",
210
+ "normalize_features": false,
211
+ "num_attention_heads": 12,
212
+ "num_hidden_layers": 12,
213
+ "pad_token_id": 0,
214
+ "pooler_dropout": 0,
215
+ "pooler_hidden_act": "gelu",
216
+ "pooler_hidden_size": 768,
217
+ "pooling_strategy": "avg",
218
+ "pos_att_type": null,
219
+ "position_biased_input": true,
220
+ "problem_type": "single_label_classification",
221
+ "projector_hidden_act": "gelu",
222
+ "prompt_first": true,
223
+ "relative_attention": false,
224
+ "scorer_type": "simple",
225
+ "squeeze_layers": false,
226
+ "text_token_index": 128002,
227
+ "torch_dtype": "float32",
228
+ "transformers_version": "4.48.2",
229
+ "type_vocab_size": 0,
230
+ "use_lstm": false,
231
+ "vocab_size": 128003
232
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd2e61f23063a5d0df96dbb92b4b19f5ae8417047b01adbcfbdb6bd719f70bc
3
+ size 737376356